tree 0a9e0bae6c2827b439590d8b1353d89f3c4a2334
parent 14d11df96336e9d06a4c8108b61815ad94866519
author liuhongt <hongtao.liu@intel.com> 1669211889 +0800
committer liuhongt <hongtao.liu@intel.com> 1669597371 +0800

Fix incorrect _mm_cvtsbh_ss.

After supporting real __bf16, the implementation of _mm_cvtsbh_ss went
wrong.

The patch add a builtin to generate pslld for the intrinsic, also
extendbfsf2 is supported with pslld when !HONOR_NANS (BFmode).

truncsfbf2 is supported with vcvtneps2bf16 when
!HONOR_NANS (BFmode) && flag_unsafe_math_optimizations.

gcc/ChangeLog:

	PR target/107748
	* config/i386/avx512bf16intrin.h (_mm_cvtsbh_ss): Refined.
	* config/i386/i386-builtin-types.def (FLOAT_FTYPE_BFLOAT16):
	New function type.
	* config/i386/i386-builtin.def (BDESC): New builtin.
	* config/i386/i386-expand.cc (ix86_expand_args_builtin):
	Handle the builtin.
	* config/i386/i386.md (extendbfsf2): New expander.
	(extendbfsf2_1): New define_insn.
	(truncsfbf2): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/avx512bf16-cvtsbh2ss-1.c: Scan pslld.
	* gcc.target/i386/extendbfsf.c: New test.